Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2647 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.7989. Min Act: -0.1700

Data Index: 6718147 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.6611. Min Act: -0.1700

Data Index: 4225042 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.5805. Min Act: -0.1700

Data Index: 2516239 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.5395. Min Act: -0.1700

Data Index: 5533886 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.5734. Min Act: -0.1700

Data Index: 4762379 (Open Web Text)

Max Activating Token Index: 798

Text #5

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.5393. Min Act: -0.1700

Data Index: 6824420 (Open Web Text)

Max Activating Token Index: 882

Text #6

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.5420. Min Act: -0.1700

Data Index: 2075559 (Open Web Text)

Max Activating Token Index: 55

Text #7

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.5141. Min Act: -0.1700

Data Index: 68179 (Open Web Text)

Max Activating Token Index: 871

Text #8

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.5377. Min Act: -0.1700

Data Index: 2114289 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4553. Min Act: -0.1700

Data Index: 5088026 (Open Web Text)

Max Activating Token Index: 999

Text #10

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4879. Min Act: -0.1700

Data Index: 5141759 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4810. Min Act: -0.1700

Data Index: 8095998 (Open Web Text)

Max Activating Token Index: 481

Text #12

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4631. Min Act: -0.1700

Data Index: 5769741 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4372. Min Act: -0.1700

Data Index: 96306 (Open Web Text)

Max Activating Token Index: 1009

Text #14

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4540. Min Act: -0.1700

Data Index: 6524774 (Open Web Text)

Max Activating Token Index: 907

Text #15

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4283. Min Act: -0.1700

Data Index: 7902436 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4597. Min Act: -0.1700

Data Index: 6721577 (Open Web Text)

Max Activating Token Index: 429

Text #17

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4689. Min Act: -0.1700

Data Index: 4218232 (Open Web Text)

Max Activating Token Index: 449

Text #18

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4516. Min Act: -0.1700

Data Index: 6115506 (Open Web Text)

Max Activating Token Index: 843

Text #19

Max Range: 4.7989. Min Range: -4.7989

Max Act: 4.4454. Min Act: -0.1700

Data Index: 3863662 (Open Web Text)

Max Activating Token Index: 170